natural-language-processing-8

Zero-shot Slot Filling

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in zero-shot-slot-filling-8

Trend

Dataset

Best Model

Actions

T-REx

zsRE

MASSIVE

Libraries

i

Use these libraries to find zero-shot-slot-filling-8 models and implementations

Datasets

T-REx

MASSIVE

KAMEL

Subtasks

No subtasks available.

Most implemented papers

MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages

P. Natarajan, Jack G. M. FitzGerald, C. Hench, Charith Peris, Scott Mackie, Kay Rottmann, A. Sánchez, Aaron Nash, Liam Urbach, Vishesh Kakarala, Richa Singh, Swetha Ranganath, Laurie Crist, Misha Britan, Wouter Leeuwis, Gokhan Tur•Sun Apr 17 2022

The MASSIVE dataset–Multilingual Amazon Slu resource package (SLURP) for Slot-filling, Intent classification, and Virtual assistant Evaluation is presented and modeling results on XLM-R and mT5 are presented, including exact match accuracy, intent classification accuracy, and slot- filling F1 score.

Content

173 0

Paper Graph

Zero-shot Slot Filling with DPR and RAG

A. Gliozzo, Michael R. Glass, Gaetano Rossiello•Fri Apr 16 2021

Several strategies are described to improve the retriever and the generator of RAG in order to make it a better slot filler, which reached the top-1 position on the KILT leaderboard on both T-REx and zsRE dataset with a large margin.

1 0

Paper Graph

Robust Retrieval Augmented Generation for Zero-shot Slot Filling

A. Gliozzo, Michael R. Glass, Gaetano Rossiello, Md. Faisal Mahbub Chowdhury•Mon Aug 30 2021

A novel approach to zero-shot slot filling that extends dense passage retrieval with hard negatives and robust training procedures for retrieval augmented generation models and demonstrates the robustness of the system showing its domain adaptation capability on a new variant of the TACRED dataset for slot filling.

36 0

Paper Graph

Robust Zero-Shot Cross-Domain Slot Filling with Example Values

Dilek Z. Hakkani-Tür, Raghav Gupta, Darsh J. Shah, Amir Fayazi•Sun Jun 16 2019

This work proposes utilizing both the slot description and a small number of examples of slot values, which may be easily available, to learn semantic representations of slots which are transferable across domains and robust to misaligned schemas.

91 0

Paper Graph

Bridge to Target Domain by Prototypical Contrastive Learning and Label Confusion: Re-explore Zero-Shot Learning for Slot Filling

Liwen Wang, Xuefeng Li, Jiachi Liu, Keqing He, Yuanmeng Yan, Weiran Xu•Wed Oct 06 2021

A novel approach based on prototypical contrastive learning with a dynamic label confusion strategy for zero-shot slot filling to establish the label dependence between the source domains and the target domain on-the-fly.

30 0

Paper Graph

GenSF: Simultaneous Adaptation of Generative Pre-trained Models and Slot Filling

Shikib Mehri, M. Eskénazi•Sat Jun 12 2021

GENSF (Generative Slot Filling), which leverages a generative pre-trained open-domain dialog model for slot filling, achieves state-of-the-art results on two slot filling datasets with strong gains in few-shot and zero-shot settings.

16 0

Paper Graph

A Multi-Task BERT Model for Schema-Guided Dialogue State Tracking

A. Potamianos, Eleftherios Kapelonis, Efthymios Georgiou•Fri Jul 01 2022

This work proposes a single multi-task BERT-based model that jointly solves the three DST tasks of intent prediction, requested slot prediction and slot filling and proposes an efficient and parsimonious encoding of the dialogue history and service schemata that is shown to further improve performance.

8 0

Paper Graph

Re2G: Retrieve, Rerank, Generate

A. Gliozzo, Michael R. Glass, Gaetano Rossiello, Md. Faisal Mahbub Chowdhury, Ankita Rajaram Naik, Pengshan Cai•Tue Jul 12 2022

This work proposes Re2G, which combines both neural initial retrieval and reranking into a BART-based sequence-to-sequence generation, and introduces a novel variation of knowledge distillation to train the initial retrieval, reranker and generation using only ground truth on the target sequence output.

138 0

Paper Graph

HierarchicalContrast: A Coarse-to-Fine Contrastive Learning Framework for Cross-Domain Zero-Shot Slot Filling

Junwen Zhang, Yin Zhang•Thu Oct 12 2023

A coarse- to fine-grained contrastive learning based on Gaussian-distributed embedding to learn the generalized deep semantic relations between utterance-tokens, by optimizing inter- and intra-token distribution distance is proposed.

5 0

Paper Graph

Adaptive End-to-End Metric Learning for Zero-Shot Cross-Domain Slot Filling

Yuanjun Shi, Linzhi Wu, Minglai Shao•Sun Oct 22 2023

A cascade-style joint learning framework coupled with context-aware soft label representations and slot-level contrastive representation learning to mitigate the data and label shift problems effectively and demonstrate the superiority of the proposed approach over a series of competitive baselines.

8 0

Paper Graph

Adding a benchmark result helps the community track progress.